Election polling is a tough business. My former YouGov colleague Chris Curtis let the cat out of the company’s bag today. On Twitter, he detailed how the team second-guessed their own polls showing a shrinking Tory lead and likely hung parliament before the 2017 election. After being off on several high-profile predictions they were put under enormous pressure to not get it wrong, and ultimately tweaked their methods in subsequent polls.
We now know that was incorrect. YouGov’s adjustment turned an excellent poll into a mediocre one. The Tory lead in votes was just 2.5 percentage points, and Theresa May lost her majority. So YouGov was mistaken to adjust its final poll, but was it a culpable mistake? This is a much harder question to answer.
